Arindam Chaudhuri

Arindam Chaudhuri

With constant growth of civilization and modernization of cities all across the world since past few centuries smart traffic management of vehicles is one of the most sorted after problem by research community. It is a challenging problem in computer vision and artificial intelligence domain. Smart traffic management basically involves segmentation of vehicles, estimation of traffic density and tracking of vehicles. The vehicle segmentation from traffic videos helps realization of niche applications such as monitoring of speed and estimation of traffic. When occlusions, background with clutters and traffic with density variations are present, this problem becomes more intractable in nature. Keeping this motivation in this research work, we investigate Faster R-CNN based deep learning method towards segmentation of vehicles. This problem is addressed in four steps viz minimization with adaptive background model, Faster R-CNN based subnet operation, Faster R-CNN initial refinement and result optimization with extended topological active nets. The computational framework uses ideas of adaptive background modeling. It also addresses shadow and illumination related issues. Higher segmentation accuracy is achieved through topological active net deformable models. The topological and extended topological active nets help to achieve stated deformations. Mesh deformation is achieved with minimization of energy. The segmentation accuracy is improved with modified version of extended topological active net. The experimental results demonstrate superiority of this computational framework

Arindam Chaudhuri

Human beings rely heavily on estimation of poses in order to access their body movements. Human pose estimation methods take advantage of computer vision advances in order to track human body movements in real life applications. This comes from videos which are recorded through available devices. These para-digms provide potential to make human movement measurement more accessible to users. The consumers of pose estimation movements believe that human poses content tend to supplement available videos. This has increased pose estimation software usage to estimate human poses. In order to address this problem, we develop hybrid-ensemble-based group pose estimation method to improve human health. This proposed hybrid-ensemble-based group pose estimation method aims to detect multi-person poses using modified group pose estimation and modified real time pose estimation. This ensemble allows fusion of performance of stated methods in real time. The input poses from images are fed into individual meth-ods. The pose transformation method helps to identify relevant features for en-semble to perform training effectively. After this, customized pre-trained hybrid ensemble is trained on public benchmarked datasets which is being evaluated through test datasets. The effectiveness and viability of proposed method is estab-lished based on comparative analysis of group pose estimation methods and ex-periments conducted on benchmarked datasets. It provides best optimized results in real-time pose estimation. It makes pose estimation method more robust to oc-clusion and improves dense regression accuracy. These results have affirmed po-tential application of this method in several real-time situations with improvement in human health life span

Arindam Chaudhuri

BSplines are one of the most promising curves in computer graphics. They are blessed with some superior geometric properties which make them an ideal candidate for several applications in computer aided design industry. In this article, some basic properties of B-Spline curves are presented. Two significant B-Spline properties viz convex hull property and repeated points effects are discussed. The BSplines computation in computational devices is also illustrated. An industry application based on image processing where B-Spline curve reconstructs the 3D surfaces for CT image datasets of inner organs further highlights the strength of these curves

Aashna Ahuja, Arindam Chaudhuri

With ever increasing number of vehicles, vehicular tracking is one of the major challenges faced by urban areas. In this paper we try to develop a model that can locate a particular vehicle that the user is looking for depending on two factors 1. the Type of vehicle and the 2. License plate number of the car. The proposed system uses a unique mixture consisting of Mask R-CNN model for vehicle type detection, WpodNet and pytesseract for License Plate detection and Prediction of letters in it.

Arindam Chaudhuri

Connected vehicle fleets are deployed worldwide in several industrial IoT scenarios. With the gradual increase of machines being controlled and managed through networked smart devices, the predictive maintenance potential grows rapidly. Predictive maintenance has the potential of optimizing uptime as well as performance such that time and labor associated with inspections and preventive maintenance are reduced. In order to understand the trends of vehicle faults with respect to important vehicle attributes viz mileage, age, vehicle type etc this problem is addressed through hierarchical modified fuzzy support vector machine (HMFSVM). The proposed method is compared with other commonly used approaches like logistic regression, random forests and support vector machines. This helps better implementation of telematics data to ensure preventative management as part of the desired solution. The superiority of the proposed method is highlighted through several experimental results.

Arindam Chaudhuri

The research presents epsilon hierarchical fuzzy twin support vector regression based on epsilon fuzzy twin support vector regression and epsilon twin support vector regression. Epsilon FTSVR is achieved by incorporating trapezoidal fuzzy numbers to epsilon TSVR which takes care of uncertainty existing in forecasting problems. Epsilon FTSVR determines a pair of epsilon insensitive proximal functions by solving two related quadratic programming problems. The structural risk minimization principle is implemented by introducing regularization term in primal problems of epsilon FTSVR. This yields dual stable positive definite problems which improves regression performance. Epsilon FTSVR is then reformulated as epsilon HFTSVR consisting of a set of hierarchical layers each containing epsilon FTSVR. Experimental results on both synthetic and real datasets reveal that epsilon HFTSVR has remarkable generalization performance with minimum training time.

Arindam Chaudhuri, Dipak Chatterjee, Ritesh Rajput

Multiple Air Vehicles (AVs) to prosecute geographically dispersed targets is an important optimization problem. Associated multiple tasks viz., target classification, attack and verification are successively performed on each target. The optimal minimum time performance of these tasks requires cooperation among vehicles such that critical time constraints are satisfied i.e. target must be classified before it can be attacked and AV is sent to target area to verify its destruction after target has been attacked. Here, optimal task scheduling problem from Indian Air Force is formulated as Fuzzy Mixed Integer Linear Programming (FMILP) problem. The solution assigns all tasks to vehicles and performs scheduling in an optimal manner including scheduled staged departure times. Coupled tasks involving time and task order constraints are addressed. When AVs have sufficient endurance, existence of optimal solution is guaranteed. The solution developed can serve as an effective heuristic for different categories of AV optimization problems.

Arindam Chaudhuri, Dipak Chatterjee

Mixed Integer Optimization has been a topic of active research in past decades. It has been used to solve Statistical problems of classification and regression involving massive data. However, there is an inherent degree of vagueness present in huge real life data. This impreciseness is handled by Fuzzy Sets. In this Paper, Fuzzy Mixed Integer Optimization Method (FMIOM) is used to find solution to Regression problem. The methodology exploits discrete character of problem. In this way large scale problems are solved within practical limits. The data points are separated into different polyhedral regions and each region has its own distinct regression coefficients. In this attempt, an attention is drawn to Statistics and Data Mining community that Integer Optimization can be significantly used to revisit different Statistical problems. Computational experimentations with generated and real data sets show that FMIOM is comparable to and often outperforms current leading methods. The results illustrate potential for significant impact of Fuzzy Integer Optimization methods on Computational Statistics and Data Mining.

Arindam Chaudhuri

Support Vector Machine (SVM) is powerful classification technique based on the idea of structural risk minimization. Use of kernel function enables curse of dimensionality to be addressed. However, proper kernel function for certain problem is dependent on specific dataset and as such there is no good method on choice of kernel function. In this paper, SVM is used to build empirical models of currency crisis in Argentina. An estimation technique is developed by training model on real life data set which provides reasonably accurate model outputs and helps policy makers to identify situations in which currency crisis may happen. The third and fourth order polynomial kernel is generally best choice to achieve high generalization of classifier performance. SVM has high level of maturity with algorithms that are simple, easy to implement, tolerates curse of dimensionality and good empirical performance. The satisfactory results show that currency crisis situation is properly emulated using only small fraction of database and could be used as an evaluation tool as well as an early warning system. To the best of knowledge this is the first work on SVM approach for currency crisis evaluation of Argentina.

Arindam Chaudhuri

We present a dynamic algorithm for solving the Longest Common Subsequence Problem using Ant Colony Optimization Technique. The Ant Colony Optimization Technique has been applied to solve many problems in Optimization Theory, Machine Learning and Telecommunication Networks etc. In particular, application of this theory in NP-Hard Problems has a remarkable significance. Given two strings, the traditional technique for finding Longest Common Subsequence is based on Dynamic Programming which consists of creating a recurrence relation and filling a table of size . The proposed algorithm draws analogy with behavior of ant colonies function and this new computational paradigm is known as Ant System. It is a viable new approach to Stochastic Combinatorial Optimization. The main characteristics of this model are positive feedback, distributed computation, and the use of constructive greedy heuristic. Positive feedback accounts for rapid discovery of good solutions, distributed computation avoids premature convergence and greedy heuristic helps find acceptable solutions in minimum number of stages. We apply the proposed methodology to Longest Common Subsequence Problem and give the simulation results. The effectiveness of this approach is demonstrated by efficient Computational Complexity. To the best of our knowledge, this is the first Ant Colony Optimization Algorithm for Longest Common Subsequence Problem.

Arindam Chaudhuri, Kajal De

Fuzzy regression models have been applied to several Operations Research applications viz., forecasting and prediction. Earlier works on fuzzy regression analysis obtain crisp regression coefficients for eliminating the problem of increasing spreads for the estimated fuzzy responses as the magnitude of the independent variable increases. But they cannot deal with the problem of non-uniform spreads. In this work, a three-phase approach is discussed to construct the fuzzy regression model with non-uniform spreads to deal with this problem. The first phase constructs the membership functions of the least-squares estimates of regression coefficients based on extension principle to completely conserve the fuzziness of observations. They are then defuzzified by the centre of area method to obtain crisp regression coefficients in the second phase. Finally, the error terms of the method are determined by setting each estimated spread equal to its corresponding observed spread. The Tagaki-Sugeno inference system is used for improving the accuracy of forecasts. The simulation example demonstrates the strength of fuzzy linear regression model in terms of higher explanatory power and forecasting performance.

Arindam Chaudhuri, Kajal De

ETP is NP Hard combinatorial optimization problem. It has received tremendous research attention during the past few years given its wide use in universities. In this Paper, we develop three mathematical models for NSOU, Kolkata, India using FILP technique. To deal with impreciseness and vagueness we model various allocation variables through fuzzy numbers. The solution to the problem is obtained using Fuzzy number ranking method. Each feasible solution has fuzzy number obtained by Fuzzy objective function. The different FILP technique performance are demonstrated by experimental data generated through extensive simulation from NSOU, Kolkata, India in terms of its execution times. The proposed FILP models are compared with commonly used heuristic viz. ILP approach on experimental data which gives an idea about quality of heuristic. The techniques are also compared with different Artificial Intelligence based heuristics for ETP with respect to best and mean cost as well as execution time measures on Carter benchmark datasets to illustrate its effectiveness. FILP takes an appreciable amount of time to generate satisfactory solution in comparison to other heuristics. The formulation thus serves as good benchmark for other heuristics. The experimental study presented here focuses on producing a methodology that generalizes well over spectrum of techniques that generates significant results for one or more datasets. The performance of FILP model is finally compared to the best results cited in literature for Carter benchmarks to assess its potential. The problem can be further reduced by formulating with lesser number of allocation variables it without affecting optimality of solution obtained. FLIP model for ETP can also be adapted to solve other ETP as well as combinatorial optimization problems.

Arindam Chaudhuri, Kajal De, Dipak Chatterjee

In India financial markets have existed for many years. A functionally accented, diverse, efficient and flexible financial system is vital to the national objective of creating a market driven, productive and competitive economy. Today markets of varying maturity exist in equity, debt, commodities and foreign exchange. In this work we attempt to generate prediction rules scheme for stock price movement at Bombay Stock Exchange using an important Soft Computing paradigm viz., Rough Fuzzy Multi Layer Perception. The use of Computational Intelligence Systems such as Neural Networks, Fuzzy Sets, Genetic Algorithms, etc. for Stock Market Predictions has been widely established. The process is to extract knowledge in the form of rules from daily stock movements. These rules can then be used to guide investors. To increase the efficiency of the prediction process, Rough Sets is used to discretize the data. The methodology uses a Genetic Algorithm to obtain a structured network suitable for both classification and rule extraction. The modular concept, based on divide and conquer strategy, provides accelerated training and a compact network suitable for generating a minimum number of rules with high certainty values. The concept of variable mutation operator is introduced for preserving the localized structure of the constituting Knowledge Based sub-networks, while they are integrated and evolved. Rough Set Dependency Rules are generated directly from the real valued attribute table containing Fuzzy membership values. The paradigm is thus used to develop a rule extraction algorithm. The extracted rules are compared with some of the related rule extraction techniques on the basis of some quantitative performance indices. The proposed methodology extracts rules which are less in number, are accurate, have high certainty factor and have low confusion with less computation time.

Arindam Chaudhuri, Kajal De, Dipak Chatterjee et al.

Transportation Problem is an important problem which has been widely studied in Operations Research domain. It has been often used to simulate different real life problems. In particular, application of this Problem in NP Hard Problems has a remarkable significance. In this Paper, we present the closed, bounded and non empty feasible region of the transportation problem using fuzzy trapezoidal numbers which ensures the existence of an optimal solution to the balanced transportation problem. The multivalued nature of Fuzzy Sets allows handling of uncertainty and vagueness involved in the cost values of each cells in the transportation table. For finding the initial solution of the transportation problem we use the Fuzzy Vogel Approximation Method and for determining the optimality of the obtained solution Fuzzy Modified Distribution Method is used. The fuzzification of the cost of the transportation problem is discussed with the help of a numerical example. Finally, we discuss the computational complexity involved in the problem. To the best of our knowledge, this is the first work on obtaining the solution of the transportation problem using fuzzy trapezoidal numbers.

Arindam Chaudhuri, Kajal De

Transportation Problem is an important aspect which has been widely studied in Operations Research domain. It has been studied to simulate different real life problems. In particular, application of this Problem in NP- Hard Problems has a remarkable significance. In this Paper, we present a comparative study of Transportation Problem through Probabilistic and Fuzzy Uncertainties. Fuzzy Logic is a computational paradigm that generalizes classical two-valued logic for reasoning under uncertainty. In order to achieve this, the notation of membership in a set needs to become a matter of degree. By doing this we accomplish two things viz., (i) ease of describing human knowledge involving vague concepts and (ii) enhanced ability to develop cost-effective solution to real-world problem. The multi-valued nature of Fuzzy Sets allows handling uncertain and vague information. It is a model-less approach and a clever disguise of Probability Theory. We give comparative simulation results of both approaches and discuss the Computational Complexity. To the best of our knowledge, this is the first work on comparative study of Transportation Problem using Probabilistic and Fuzzy Uncertainties.

Arindam Chaudhuri

Fuzzy Set Theory has been applied in many fields such as Operations Research, Control Theory, and Management Sciences etc. In particular, an application of this theory in Managerial Decision Making Problems has a remarkable significance. In this Paper, we consider a solution of Rectangular Fuzzy game with pay-off as imprecise numbers instead of crisp numbers viz., interval and LR-type Trapezoidal Fuzzy Numbers. The solution of such Fuzzy games with pure strategies by minimax-maximin principle is discussed. The Algebraic Method to solve Fuzzy games without saddle point by using mixed strategies is also illustrated. Here, pay-off matrix is reduced to pay-off matrix by Dominance Method. This fact is illustrated by means of Numerical Example.

Arindam Chaudhuri, Kajal De, Dipak Chatterjee

Neuro-Fuzzy Modeling has been applied in a wide variety of fields such as Decision Making, Engineering and Management Sciences etc. In particular, applications of this Modeling technique in Decision Making by involving complex Systems of Linear Algebraic Equations have remarkable significance. In this Paper, we present Polak-Ribiere Conjugate Gradient based Neural Network with Fuzzy rules to solve System of Simultaneous Linear Algebraic Equations. This is achieved using Fuzzy Backpropagation Learning Rule. The implementation results show that the proposed Neuro-Fuzzy Network yields effective solutions for exactly determined, underdetermined and over-determined Systems of Linear Equations. This fact is demonstrated by the Computational Complexity analysis of the Neuro-Fuzzy Algorithm. The proposed Algorithm is simulated effectively using MATLAB software. To the best of our knowledge this is the first work of the Systems of Linear Algebraic Equations using Neuro-Fuzzy Modeling.

Arindam Chaudhuri, Kajal De, Dipak Chatterjee

The Fuzzy Modeling has been applied in a wide variety of fields such as Engineering and Management Sciences and Social Sciences to solve a number Decision Making Problems which involve impreciseness, uncertainty and vagueness in data. In particular, applications of this Modeling technique in Decision Making Problems have remarkable significance. These problems have been tackled using various theories such as Probability theory, Fuzzy Set Theory, Rough Set Theory, Vague Set Theory, Approximate Reasoning Theory etc. which lack in parameterization of the tools due to which they could not be applied successfully to such problems. The concept of Soft Set has a promising potential for giving an optimal solution for these problems. With the motivation of this new concept, in this paper we define the concepts of Soft Relation and Fuzzy Soft Relation and then apply them to solve a number of Decision Making Problems. The advantages of Fuzzy Soft Relation compared to other paradigms are discussed. To the best of our knowledge this is the first work on the application of Fuzzy Soft Relation to the Decision Making Problems.